© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10619
    Prev
    Next
    INDEX
    Explanations

    lung cancer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主ä¹ī
    -0.10
     лиÑĨ
    -0.10
    ennon
    -0.10
    etable
    -0.09
    主義
    -0.09
    ../../../
    -0.09
    abad
    -0.09
    åĽ¢éķ¿
    -0.09
    å®ł
    -0.09
    dn
    -0.09
    POSITIVE LOGITS
    -mouth
    0.10
    èĦ¯
    0.09
    itting
    0.08
     Lair
    0.08
    积水
    0.08
    LESS
    0.08
    walk
    0.08
    roup
    0.08
    åªĴ
    0.08
    ç¦ıå¾·
    0.08
    Activations Density 0.063%

    No Known Activations